{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,10]],"date-time":"2026-11-10T13:35:56Z","timestamp":1794317756384,"version":"4.9.0"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,12,17]],"date-time":"2022-12-17T00:00:00Z","timestamp":1671235200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,17]],"date-time":"2022-12-17T00:00:00Z","timestamp":1671235200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,12,17]]},"DOI":"10.1109\/bigdata55660.2022.10021125","type":"proceedings-article","created":{"date-parts":[[2023,1,26]],"date-time":"2023-01-26T19:35:23Z","timestamp":1674761723000},"page":"1356-1361","source":"Crossref","is-referenced-by-count":1,"title":["Critic-over-Actor-Critic Modeling: Finding Optimal Strategy in ICU Environments"],"prefix":"10.1109","author":[{"given":"Riazat","family":"Ryan","sequence":"first","affiliation":[{"name":"University of Massachusetts Dartmouth,Department of Computer and Information Science,North Dartmouth,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming","family":"Shao","sequence":"additional","affiliation":[{"name":"University of Massachusetts Dartmouth,Department of Computer and Information Science,North Dartmouth,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Symmetry in markov decision processes and its implications for single agent and multi agent learning","volume-title":"Proceedings of the 18th International Conference on Machine Learning","author":"Zinkevich"},{"key":"ref2","article-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar6404"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-18305-9_46"},{"key":"ref5","article-title":"The starcraft multi-agent challenge","author":"Samvelyan","year":"2019"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref7","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume":"30","author":"Lowe","year":"2017","journal-title":"Advances in NeurIPS"},{"key":"ref8","article-title":"Robust deep reinforcement learning through adversarial loss","volume":"34","author":"Oikarinen","year":"2021","journal-title":"Advances in NeurIPS"},{"key":"ref9","first-page":"5774","article-title":"Offline reinforcement learning with fisher divergence critic regularization","volume-title":"ICML","author":"Kostrikov"},{"key":"ref10","first-page":"2961","article-title":"Actor-attention-critic for multi-agent reinforcement learning","volume-title":"ICML","author":"Iqbal"},{"key":"ref11","article-title":"Soft actor-critic algorithms and applications","author":"Haarnoja","year":"2018"},{"key":"ref12","volume-title":"Deep Reinforcement Learning Hands-On: Apply modern RL methods, with deep Q-networks, value iteration, policy gradients, TRPO, AlphaGo Zero and more.","author":"Lapan","year":"2018"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/1329125.1329172"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71682-4_5"},{"key":"ref15","first-page":"1804","article-title":"Opponent modeling in deep reinforcement learning","volume-title":"ICML","author":"He"},{"key":"ref16","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume":"12","author":"Sutton","year":"1999","journal-title":"Advances in NeurIPS"},{"key":"ref17","article-title":"Decision-aware model learning for actor-critic methods: when theory does not meet practice","author":"Lovatto","year":"2020"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.23919\/ACC45564.2020.9147960"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2016.35"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1002\/sim.3720"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICSSE.2010.5551776"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.biosystems.2011.07.005"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-018-0213-5"},{"key":"ref24","article-title":"Deep reinforcement learning for sepsis treatment","author":"Raghu","year":"2017"},{"key":"ref25","first-page":"147","article-title":"Continuous state-space models for optimal sepsis treatment: a deep reinforcement learning approach","volume-title":"Machine Learning for Healthcare Conference","author":"Raghu"},{"key":"ref26","article-title":"The actor search tree critic (astc) for off-policy pomdp learning in medical decision making","author":"Li","year":"2018"},{"key":"ref27","article-title":"Health-informed policy gradients for multi-agent reinforcement learning","author":"Allen","year":"2019"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3390\/cancers13184624"},{"key":"ref29","article-title":"Pettingzoo: Gym for multi-agent reinforcement learning","volume":"34","author":"Terry","year":"2021","journal-title":"Advances in NeurIPS"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/BigData47090.2019.9005602"},{"key":"ref31","article-title":"Sepsis world model: A mimic-based openai gym","author":"Kiani","year":"2019","journal-title":"world model\" simulator for sepsis treatment"}],"event":{"name":"2022 IEEE International Conference on Big Data (Big Data)","location":"Osaka, Japan","start":{"date-parts":[[2022,12,17]]},"end":{"date-parts":[[2022,12,20]]}},"container-title":["2022 IEEE International Conference on Big Data (Big Data)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10020192\/10020156\/10021125.pdf?arnumber=10021125","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T06:08:03Z","timestamp":1707804483000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10021125\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,17]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/bigdata55660.2022.10021125","relation":{},"subject":[],"published":{"date-parts":[[2022,12,17]]}}}